Skip to main content
OpenAI

API Pricing

Contact sales

Our latest models

Reasoning models for complex, multi-step problems

OpenAI o1

Frontier reasoning model that supports tools, Structured Outputs, and vision | 200k context length

Price

Input:
$15.00 / 1M tokens
Cached input:
$7.50 / 1M tokens
Output:
$60.00 / 1M tokens

OpenAI o3-mini

Small cost-efficient reasoning model that’s optimized for coding, math, and science, and supports tools and Structured Outputs | 200k context length

Price

Input:
$1.10 / 1M tokens
Cached input:
$0.55 / 1M tokens
Output:
$4.40 / 1M tokens

Save 50% on inputs and outputs with the Batch API⁠(opens in a new window) and run tasks asynchronously over 24 hours.

GPT models for everyday tasks

GPT-4.5

Largest GPT model designed for creative tasks and agentic planning, currently available in a research preview | 128k context length

Price

Input:
$75.00 / 1M tokens
Cached input:
$37.50 / 1M tokens
Output:
$150.00 / 1M tokens

GPT-4o

High-intelligence model for complex tasks | 128k context length

Price

Input:
$2.50 / 1M tokens
Cached input:
$1.25 / 1M tokens
Output:
$10.00 / 1M tokens

GPT-4o mini

Affordable small model for fast, everyday tasks | 128k context length

Price

Input:
$0.150 / 1M tokens
Cached input:
$0.075 / 1M tokens
Output:
$0.600 / 1M tokens

Save 50% on inputs and outputs with the Batch API⁠(opens in a new window) and run tasks asynchronously over 24 hours.

Fine-tuning our models

Customize our models to get even higher performance for your specific use cases.

GPT-4o

Fine-tuning price

Input:
$3.750 / 1M tokens
Cached input:
$1.875 / 1M tokens
Output:
$15.000 / 1M tokens
Training:
$25.000 / 1M tokens

GPT-4o mini

Fine-tuning price

Input:
$0.30 / 1M tokens
Cached input:
$0.15 / 1M tokens
Output:
$1.20 / 1M tokens
Training:
$3.00 / 1M tokens

You can also fine-tune our legacy models⁠(opens in a new window).

Our APIs

Realtime API

Build low-latency, multimodal experiences including speech-to-speech.

GPT-4o
$5.00 / 1M input tokens
$2.50 / 1M cached input tokens
$20.00 / 1M output tokens
GPT-4o mini
$0.60 / 1M input tokens
$0.30 / 1M cached input tokens
$2.40 / 1M output tokens

Responses API

Our newest API combining the simplicity of Chat Completions with the built-in tool use of Assistants.

Price
Responses API is not priced separately. Tokens are billed at the chosen language model’s input and output rates.

Chat Completions API

Build text-based conversational experiences.

Price
Chat Completions API is not priced separately. Tokens are billed at the chosen language model's input and output rates.

Assistants API

Build assistant-like experiences with our tools.

Price
Assistants API is not priced separately. Tokens are billed at the chosen language model's input and output rates.

Built-in tools

Extend model capabilities with built-in tools in the API Platform

Code Interpreter
$0.03
File Search Storage
$0.10 / GB of vector storage per day (first GB free)
File Search Tool Call (Responses API only)
$2.50 / 1k tool calls
Web Search Tool Call
Pricing depends on model and search context size. See below.
gpt-4o and gpt-4o-search-preview
search_context_size low:
$30.00 / 1K calls
search_context_size medium (default):
$35.00 / 1K calls
search_context_size high:
$50.00 / 1K calls
gpt-4o-mini and gpt-4o-mini-search-preview
search_context_size low:
$25.00 / 1K calls
search_context_size medium (default):
$27.50 / 1K calls
search_context_size high:
$30.00 / 1K calls
GB refers to binary gigabytes of storage (also known as gibibyte), where 1GB is 2^30 bytes.

FAQ

We recommend that developers use GPT‑4o or GPT‑4o mini for everyday tasks. GPT‑4o generally performs better on a wide range of tasks, while GPT‑4o mini is fast and inexpensive for simpler tasks. Our o1 reasoning models are ideal for complex, multi-step tasks and STEM use cases that require deep thinking about tough problems. We recommend experimenting with all of these models in the Playground⁠(opens in a new window) to explore which models provide the best price performance trade-off for your usage.

Start creating with OpenAI’s powerful models.

Get startedContact sales